INDEX

Explanations

opportunity

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pact

-0.28

åį¯

-0.27

covered

-0.26

iens

-0.25

æªĢ

-0.25

asca

-0.25

relation

-0.25

 covered

-0.24

()._

-0.24

æ¾ľ

-0.24

POSITIVE LOGITS

EEE

0.29

 ANSI

0.29

Ì

0.27

è®¤å®ļ

0.27

fir

0.25

opic

0.25

ãĤīãģı

0.25

åħħåĪĨåıĳæĮ¥

0.24

ãģ¡

0.24

ube

0.23

Activations Density 0.360%

opportunity

No Comments

No Known Activations

opportunity

No Comments

No Known Activations